© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 38725
    Prev
    Next
    INDEX
    Explanations

    organizations and institutions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĪIJ群
    -0.09
    AdapterFactory
    -0.08
    ä»¬ä¹Ł
    -0.08
    à¹Ģลà¹Īา
    -0.08
    åĢij
    -0.08
    å±Ĭåħ¨åĽ½
    -0.07
    们对
    -0.07
    ç»Ķ
    -0.07
    éķĩ人æ°ijæĶ¿åºľ
    -0.07
    们
    -0.07
    POSITIVE LOGITS
    åīį身
    0.08
    ç®Ģ称
    0.07
    ä¸ĭå±ŀ
    0.07
    åĴĮä¸Ĭæµ·
    0.07
    以ä¸ĭç®Ģ称
    0.07
    çŃīåįķä½į
    0.07
    è§Ħå®ļçļĦåħ¶ä»ĸ
    0.07
    Ø¡
    0.07
    ìĿĺ
    0.06
    æĪIJç«ĭ以æĿ¥
    0.06
    Activations Density 0.085%

    No Known Activations